Skip to content

feat(harvester): map INSPIRE urls as related identifiers #997

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
zzacharo merged 1 commit into from
Oct 2, 2026
Merged

feat(harvester): map INSPIRE urls as related identifiers #997

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 18 additions & 1 deletion site/cds_rdm/inspire_harvester/transform/mappers/identifiers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@

from flask import current_app
from idutils.normalizers import normalize_isbn, normalize_urn
from idutils.validators import is_doi, is_urn
from idutils.validators import is_doi, is_url, is_urn

from cds_rdm import schemes
from cds_rdm.inspire_harvester.transform.mappers.mapper import MapperBase
Expand Down Expand Up @@ -342,6 +342,23 @@ def map_value(self, src_record, ctx, logger):
}
)

# External links from INSPIRE (e.g. university repository pages).
for url_entry in src_metadata.get("urls", []):
value = url_entry.get("value") if isinstance(url_entry, dict) else None
if not value:
continue
if not is_url(value):
ctx.errors.append(f"Invalid URL. | details: value={value}")
continue
identifiers.append(
{
"scheme": "url",
"identifier": value,
"relation_type": {"id": "references"},
"resource_type": {"id": ctx.resource_type.value},
}
)

has_cds_doi = any(
d.get("value", "").startswith(current_app.config["DATACITE_PREFIX"])
for d in src_metadata.get("dois", [])
Expand Down
10 changes: 10 additions & 0 deletions site/tests/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1573,6 +1573,16 @@ def relation_type_v(app, relation_type):
},
)

vocab = vocabulary_service.create(
system_identity,
{
"id": "references",
"props": {"datacite": "References"},
"title": {"en": "References"},
"type": "relationtypes",
},
)

vocab = vocabulary_service.create(
system_identity,
{
Expand Down
88 changes: 88 additions & 0 deletions site/tests/inspire_harvester/test_harvester_job.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,23 @@
"publication_date": "2024",
"languages": [{"id": "eng", "title": {"en": "English", "da": "Engelsk"}}],
"related_identifiers": [
{
"identifier": "https://wigner.hu/~vertesi/publ/24-PhD-Thesis-VargaZ.pdf",
"relation_type": {
"id": "references",
"title": {
"en": "References",
},
},
"resource_type": {
"id": "publication-dissertation",
"title": {
"de": "Abschlussarbeit",
"en": "Thesis",
},
},
"scheme": "url",
},
{
"identifier": "2840463",
"relation_type": {
Expand Down Expand Up @@ -213,6 +230,40 @@
},
"scheme": "cdsrn",
},
{
"identifier": "https://tel.archives-ouvertes.fr/tel-01155127/",
"relation_type": {
"id": "references",
"title": {
"en": "References",
},
},
"resource_type": {
"id": "publication-dissertation",
"title": {
"de": "Abschlussarbeit",
"en": "Thesis",
},
},
"scheme": "url",
},
{
"identifier": "https://tel.archives-ouvertes.fr/tel-01155127",
"relation_type": {
"id": "references",
"title": {
"en": "References",
},
},
"resource_type": {
"id": "publication-dissertation",
"title": {
"de": "Abschlussarbeit",
"en": "Thesis",
},
},
"scheme": "url",
},
{
"identifier": "1452604",
"relation_type": {
Expand Down Expand Up @@ -289,6 +340,43 @@
"publication_date": "2024-05",
"languages": [{"id": "spa", "title": {"en": "Spanish"}}],
"related_identifiers": [
{
"identifier": (
"https://www.ifisica.uaslp.mx/~jurgen/"
"AkbarEmmanuelDiazRodarte-Lic.pdf"
),
"relation_type": {
"id": "references",
"title": {
"en": "References",
},
},
"resource_type": {
"id": "publication-dissertation",
"title": {
"de": "Abschlussarbeit",
"en": "Thesis",
},
},
"scheme": "url",
},
{
"identifier": "https://www.ifisica.uaslp.mx/~jurgen/Theses.html",
"relation_type": {
"id": "references",
"title": {
"en": "References",
},
},
"resource_type": {
"id": "publication-dissertation",
"title": {
"de": "Abschlussarbeit",
"en": "Thesis",
},
},
"scheme": "url",
},
{
"identifier": "2802969",
"relation_type": {
Expand Down
69 changes: 69 additions & 0 deletions site/tests/inspire_harvester/test_transformer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,75 @@ def test_transform_related_identifiers_skips_invalid_urn(running_app):
assert f"Invalid URN. | details: value={raw}" in ctx.errors


def test_transform_related_identifiers_maps_inspire_urls(running_app):
"""INSPIRE metadata.urls become related identifiers with scheme url."""
src_record = {
"metadata": {
"urls": [
{
"value": (
"https://tesidottorato.depositolegale.it/"
"handle/20.500.14242/121964"
)
},
{"value": "https://iris.unife.it/handle/11392/2549512"},
{"value": "not-a-url"},
{"value": ""},
{},
],
},
"created": "2023-01-01",
}
ctx = MetadataSerializationContext(
resource_type=ResourceType.THESIS, inspire_id="2808071"
)
logger = Logger(inspire_id="2808071")

result = RelatedIdentifiersMapper().map_value(src_record, ctx, logger)

assert {
"scheme": "url",
"identifier": (
"https://tesidottorato.depositolegale.it/handle/20.500.14242/121964"
),
"relation_type": {"id": "references"},
"resource_type": {"id": "publication-dissertation"},
} in result
assert {
"scheme": "url",
"identifier": "https://iris.unife.it/handle/11392/2549512",
"relation_type": {"id": "references"},
"resource_type": {"id": "publication-dissertation"},
} in result
assert not any(item.get("identifier") == "not-a-url" for item in result)
assert "Invalid URL. | details: value=not-a-url" in ctx.errors


def test_transform_related_identifiers_dedupes_urls(running_app):
"""Duplicate INSPIRE urls are mapped once."""
url = "https://example.org/thesis"
src_record = {
"metadata": {"urls": [{"value": url}, {"value": url}]},
"created": "2023-01-01",
}
ctx = MetadataSerializationContext(
resource_type=ResourceType.OTHER, inspire_id="1"
)
logger = Logger(inspire_id="1")

result = RelatedIdentifiersMapper().map_value(src_record, ctx, logger)

url_items = [item for item in result if item.get("scheme") == "url"]
assert url_items == [
{
"scheme": "url",
"identifier": url,
"relation_type": {"id": "references"},
"resource_type": {"id": "publication-other"},
}
]


def test_transform_identifiers(running_app):
"""Test IdentifiersMapper."""
src_metadata = {
Expand Down
Loading